# Deep MOS Predictor for Synthetic Speech Using Cluster-Based Modeling

arXiv: https://arxiv.org/abs/2008.03710 · HTML: https://mlsanity.com/paper/2008.03710/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Aug 2020.

## Built on by (most cited first, 4 of 4)

- [SOMOS: The Samsung Open MOS Dataset for the Evaluation of Neural Text-to-Speech Synthesis](https://mlsanity.com/paper/2204.03040/) (2022)
- [Generative Data Augmentation Challenge: Zero-Shot Speech Synthesis for Personalized Speech Enhancement](https://mlsanity.com/paper/2501.13372/) (2025)
- [Wideband Audio Waveform Evaluation Networks: Efficient, Accurate Estimation of Speech Qualities](https://mlsanity.com/paper/2206.13272/) (2022)
- [Voice Mapping of Text-to-Speech Systems: A Metric-Based Approach for Voice Quality Assessment](https://mlsanity.com/paper/2605.00861/) (2026)

## Abstract (arXiv)

While deep learning has made impressive progress in speech synthesis and voice conversion, the assessment of the synthesized speech is still carried out by human participants. Several recent papers have proposed deep-learning-based assessment models and shown the potential to automate the speech quality assessment. To improve the previously proposed assessment model, MOSNet, we propose three models using cluster-based modeling methods: using a global quality token (GQT) layer, using an Encoding Layer, and using both of them. We perform experiments using the evaluation results of the Voice Conversion Challenge 2018 to predict the mean opinion score of synthesized speech and similarity score between synthesized speech and reference speech. The results show that the GQT layer helps to predict human assessment better by automatically learning the useful quality tokens for the task and that the Encoding Layer helps to utilize frame-level scores more precisely.